What transport does this server use?
It uses SSE (Server‑Sent Events) with JWT Bearer token authentication.
@anisirji
Basic information
Secure middleware server implementing Model Context Protocol (MCP) over SSE with JWT authentication. Enables standardized communication between AI tools and clients with dynamic tool registration, request logging, and session management. Perfect for building production-ready AI s
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-remote-setup-with-jwt-auth": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
This server is a Model Context Protocol (MCP) SSE server that provides JWT‑based authentication for exposing multiple AI tools over an SSE transport. It is designed for developers needing secure remote access to MCP tools with flexible token management.
Clone the repository, install dependencies with npm install, create a .env file with a JWT_SECRET, and run npm run dev to start the server on http://localhost:3001/sse. Generate a JWT token via GET /auth/token?username=<username>&scope=mcp:access. Then connect to the SSE endpoint using the token in the Authorization header.
It uses SSE (Server‑Sent Events) with JWT Bearer token authentication.
Send a GET request to `/auth/token?username=<username>&scope=mcp:access`.
Default tools are `test`, `echo`, `get-time`, and `random-number`.
Node.js, Express, @modelcontextprotocol/sdk, JWT, and Zod.
It is designed to be extended for production use; upcoming changes include token revocation, role‑based access, and rate limiting.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
Comments